{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,19]],"date-time":"2026-08-19T20:14:57Z","timestamp":1787170497113,"version":"build-2736575974"},"reference-count":42,"publisher":"The Endocrine Society","issue":"10","license":[{"start":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T00:00:00Z","timestamp":1658707200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"DOI":"10.13039\/501100001505","name":"Health Research Council of New Zealand","doi-asserted-by":"publisher","award":["10\/400"],"award-info":[{"award-number":["10\/400"]}],"id":[{"id":"10.13039\/501100001505","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,9,28]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Context<\/jats:title>\n                    <jats:p>Conventional prediction models for vitamin D deficiency have limited accuracy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Using cross-sectional data, we developed models based on machine learning (ML) and compared their performance with those based on a conventional approach.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Participants were 5106 community-resident adults (50-84 years; 58% male). In the randomly sampled training set (65%), we constructed 5 ML models: lasso regression, elastic net regression, random forest, gradient boosted decision tree, and dense neural network. The reference model was a logistic regression model. Outcomes were deseasonalized serum 25-hydroxyvitamin D (25(OH)D) &amp;lt;50 nmol\/L (yes\/no) and &amp;lt;25 nmol\/L (yes\/no). In the test set (the remaining 35%), we evaluated predictive performance of each model, including area under the receiver operating characteristic curve (AUC) and net benefit (decision curves).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Overall, 1270 (25%) and 91 (2%) had 25(OH)D &amp;lt;50 and &amp;lt;25 nmol\/L, respectively. Compared with the reference model, the ML models predicted 25(OH)D &amp;lt;50 nmol\/L with similar accuracy. However, for prediction of 25(OH)D &amp;lt;25 nmol\/L, all ML models had higher AUC point estimates than the reference model by up to 0.14. AUC was highest for elastic net regression (0.93; 95% CI 0.90-0.96), compared with 0.81 (95% CI 0.71-0.91) for the reference model. In the decision curve analysis, ML models mostly achieved a greater net benefit across a range of thresholds.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Compared with conventional models, ML models predicted 25(OH)D &amp;lt;50 nmol\/L with similar accuracy but they predicted 25(OH)D &amp;lt;25 nmol\/L with greater accuracy. The latter finding suggests a role for ML models in participant selection for vitamin D supplement trials.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1210\/clinem\/dgac432","type":"journal-article","created":{"date-parts":[[2022,7,25]],"date-time":"2022-07-25T09:00:58Z","timestamp":1658739658000},"page":"2737-2747","source":"Crossref","is-referenced-by-count":11,"title":["Prediction of Vitamin D Deficiency in Older Adults: The Role of Machine Learning Models"],"prefix":"10.1210","volume":"107","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9722-139X","authenticated-orcid":false,"given":"John D","family":"Sluyter","sequence":"first","affiliation":[{"name":"School of Population Health, University of Auckland , Auckland 1023 , New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoshihiko","family":"Raita","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Massachusetts General Hospital, Harvard Medical School , Boston, MA 02115 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kohei","family":"Hasegawa","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Massachusetts General Hospital, Harvard Medical School , Boston, MA 02115 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6021-5458","authenticated-orcid":false,"given":"Ian R","family":"Reid","sequence":"additional","affiliation":[{"name":"Department of Medicine, Faculty of Medical and Health Sciences, University of Auckland , Auckland 1023 , New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Robert","family":"Scragg","sequence":"additional","affiliation":[{"name":"School of Population Health, University of Auckland , Auckland 1023 , New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Carlos A","family":"Camargo","sequence":"additional","affiliation":[{"name":"Department of Emergency Medicine, Massachusetts General Hospital, Harvard Medical School , Boston, MA 02115 , USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"80","published-online":{"date-parts":[[2022,7,25]]},"reference":[{"issue":"5","key":"2022092808430659500_CIT0001","doi-asserted-by":"crossref","first-page":"561","DOI":"10.3390\/nu10050561","article-title":"Emerging evidence of thresholds for beneficial effects from vitamin D supplementation","volume":"10","author":"Scragg","year":"2018","journal-title":"Nutrients."},{"key":"2022092808430659500_CIT0002","first-page":"356","article-title":"Vitamin D supplementation to prevent acute respiratory tract infections: systematic review and meta-analysis of individual participant data","author":"Martineau","year":"2017","journal-title":"BMJ"},{"key":"2022092808430659500_CIT0003","doi-asserted-by":"crossref","first-page":"452","DOI":"10.1111\/joim.12651","article-title":"Effect of monthly high-dose vitamin D on bone density in community-dwelling older adults substudy of a randomized controlled trial","volume":"282","author":"Reid","year":"2017","journal-title":"J Intern Med."},{"issue":"8","key":"2022092808430659500_CIT0004","doi-asserted-by":"crossref","first-page":"1464","DOI":"10.1002\/jbmr.3442","article-title":"25-hydroxyvitamin D threshold for the effects of vitamin D supplements on bone density: secondary analysis of a randomized controlled trial","volume":"33","author":"Macdonald","year":"2018","journal-title":"J Bone Miner Res."},{"issue":"12","key":"2022092808430659500_CIT0005","doi-asserted-by":"crossref","first-page":"837","DOI":"10.1016\/S2213-8587(21)00263-1","article-title":"Estimating dose-response relationships for vitamin D with coronary heart disease, stroke, and all-cause mortality: observational and Mendelian randomisation analyses","volume":"9","author":"Sofianopoulou","year":"2021","journal-title":"Lancet Diabetes Endocrinol."},{"issue":"17","key":"2022092808430659500_CIT0006","doi-asserted-by":"crossref","first-page":"3689","DOI":"10.1111\/febs.15534","article-title":"Vitamin D to prevent COVID-19: recommendations for the design of clinical trials","volume":"287","author":"Camargo","year":"2020","journal-title":"FEBS J."},{"issue":"7","key":"2022092808430659500_CIT0007","doi-asserted-by":"crossref","first-page":"e2783","DOI":"10.1097\/MD.0000000000002783","article-title":"Quick and easy screening for Vitamin D insufficiency in adults a scoring system to be implemented in daily clinical practice","volume":"95","author":"Deschasaux","year":"2016","journal-title":"Medicine (Baltimore)."},{"issue":"7","key":"2022092808430659500_CIT0008","doi-asserted-by":"crossref","first-page":"1539","DOI":"10.1007\/s00198-018-4410-3","article-title":"Prediction of insufficient serum vitamin D status in older women: a validated model","volume":"29","author":"Merlijn","year":"2018","journal-title":"Osteoporosis Int"},{"issue":"5","key":"2022092808430659500_CIT0009","doi-asserted-by":"crossref","first-page":"1089","DOI":"10.3945\/ajcn.113.076430","article-title":"Prediction of vitamin D deficiency by simple patient characteristics","volume":"99","author":"Sohl","year":"2014","journal-title":"Am J Clin Nutr."},{"issue":"5","key":"2022092808430659500_CIT0010","doi-asserted-by":"crossref","first-page":"631","DOI":"10.1111\/cen.12203","article-title":"Predicting vitamin D deficiency in older Australian adults","volume":"79","author":"Tran","year":"2013","journal-title":"Clin Endocrinol"},{"issue":"5","key":"2022092808430659500_CIT0011","doi-asserted-by":"crossref","first-page":"854","DOI":"10.1007\/s00774-018-0984-2","article-title":"A simple questionnaire for the prediction of vitamin D deficiency in Japanese adults (Vitamin D Deficiency questionnaire for Japanese: VDDQ-J)","volume":"37","author":"Kuwabara","year":"2019","journal-title":"J Bone Miner Metab."},{"issue":"4","key":"2022092808430659500_CIT0012","doi-asserted-by":"crossref","first-page":"739","DOI":"10.1017\/S1368980013001973","article-title":"Can a questionnaire predict vitamin D status in postmenopausal women?","volume":"17","author":"Nabak","year":"2014","journal-title":"Public Health Nutr."},{"issue":"2","key":"2022092808430659500_CIT0013","doi-asserted-by":"crossref","first-page":"236","DOI":"10.1017\/S136898000800356X","article-title":"Use of a questionnaire to assess vitamin D status in young adults","volume":"12","author":"Bolek-Berquist","year":"2009","journal-title":"Public Health Nutr."},{"issue":"4","key":"2022092808430659500_CIT0014","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1016\/j.maturitas.2014.05.023","article-title":"A predictive model of vitamin D insufficiency in older community people: from the S\u00e3o Paulo Aging & Health Study (SPAH)","volume":"78","author":"Lopes","year":"2014","journal-title":"Maturitas."},{"issue":"1","key":"2022092808430659500_CIT0015","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1007\/s11657-020-00844-y","article-title":"A prediction tool for vitamin D deficiency in New Zealand adults","volume":"15","author":"Narang","year":"2020","journal-title":"Arch Osteoporos."},{"issue":"2","key":"2022092808430659500_CIT0016","doi-asserted-by":"crossref","first-page":"378","DOI":"10.1038\/jid.2014.400","article-title":"Determinants of vitamin D status in Caucasian adults: influence of sun exposure, dietary intake, sociodemographic, lifestyle, anthropometric, and genetic factors","volume":"135","author":"Touvier","year":"2015","journal-title":"J Invest Dermatol."},{"key":"2022092808430659500_CIT0017","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4614-6849-3","volume-title":"Applied Predictive Modeling","author":"Kuhn","year":"2013"},{"issue":"4","key":"2022092808430659500_CIT0018","doi-asserted-by":"crossref","first-page":"e0174944","DOI":"10.1371\/journal.pone.0174944","article-title":"Can machine-learning improve cardiovascular risk prediction using routine clinical data?","volume":"12","author":"Weng","year":"2017","journal-title":"PLoS One."},{"issue":"11","key":"2022092808430659500_CIT0019","doi-asserted-by":"crossref","first-page":"e79970","DOI":"10.1371\/journal.pone.0079970","article-title":"A novel approach for prediction of vitamin D status using support vector regression","volume":"8","author":"Guo","year":"2013","journal-title":"PLoS One."},{"issue":"3","key":"2022092808430659500_CIT0020","doi-asserted-by":"crossref","first-page":"460","DOI":"10.2215\/CJN.06440909","article-title":"Clinical measures identify vitamin D deficiency in dialysis","volume":"5","author":"Bhan","year":"2010","journal-title":"Clin J Am Soc Nephrol."},{"issue":"6","key":"2022092808430659500_CIT0021","doi-asserted-by":"crossref","first-page":"536.e8","DOI":"10.1016\/j.jamda.2015.03.008","article-title":"Derivation and validation of a clinical diagnostic tool for the identification of older community-dwellers with hypovitaminosis D","volume":"16","author":"Annweiler","year":"2015","journal-title":"J Am Med Dirs Assoc."},{"issue":"5","key":"2022092808430659500_CIT0022","doi-asserted-by":"crossref","first-page":"858","DOI":"10.3945\/jn.116.244079","article-title":"Ambient UVB dose and sun enjoyment are important predictors of vitamin D status in an older population","volume":"147","author":"O\u2019Sullivan","year":"2017","journal-title":"J Nutr."},{"key":"2022092808430659500_CIT0023","doi-asserted-by":"crossref","first-page":"318","DOI":"10.1016\/j.jsbmb.2015.09.010","article-title":"The Vitamin D Assessment (ViDA) Study: design of a randomized controlled trial of vitamin D supplementation for the prevention of cardiovascular disease, acute respiratory infection, falls and non-vertebral fractures","volume":"164","author":"Scragg","year":"2016","journal-title":"J Steroid Biochem Mol Biol."},{"key":"2022092808430659500_CIT0024","volume-title":"Supplementary material for: Prediction of vitamin D deficiency in older adults: the role of machine learning models","author":"Sluyter"},{"key":"2022092808430659500_CIT0025","volume-title":"NZDep2013 Index of Deprivation","author":"Atkinson","year":"2014"},{"issue":"6","key":"2022092808430659500_CIT0026","doi-asserted-by":"crossref","first-page":"1243","DOI":"10.3945\/ajcn.112.054502","article-title":"Estimating mean annual 25-hydroxyvitamin D concentrations from single measurements: the Multi-Ethnic Study of Atherosclerosis","volume":"97","author":"Sachs","year":"2013","journal-title":"Am J Clin Nutr."},{"issue":"4","key":"2022092808430659500_CIT0027","doi-asserted-by":"crossref","first-page":"493","DOI":"10.3390\/nu10040493","article-title":"Clinical management of low vitamin D: a scoping review of physicians\u2019 practices","volume":"10","author":"Rockwell","year":"2018","journal-title":"Nutrients."},{"issue":"10","key":"2022092808430659500_CIT0028","doi-asserted-by":"crossref","first-page":"2987","DOI":"10.1210\/jc.2011-0090","article-title":"2011 report on dietary reference intake for vitamin D: where do we go from here?","volume":"96","author":"Aloia","year":"2011","journal-title":"J Clin Endocrinol Metab."},{"key":"2022092808430659500_CIT0029","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jsbmb.2018.11.016","article-title":"Cross-sectional associations of vitamin D status with asthma prevalence, exacerbations, and control in New Zealand adults","volume":"188","author":"Win","year":"2019","journal-title":"J Steroid Biochem Mol Biol."},{"key":"2022092808430659500_CIT0030","author":"Breiman","year":"2018"},{"key":"2022092808430659500_CIT0031","author":"Kuhn","year":"2019"},{"key":"2022092808430659500_CIT0032","author":"Allaire","year":"2019"},{"issue":"3","key":"2022092808430659500_CIT0033","doi-asserted-by":"crossref","first-page":"837","DOI":"10.2307\/2531595","article-title":"Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach","volume":"44","author":"DeLong","year":"1988","journal-title":"Biometrics."},{"issue":"2","key":"2022092808430659500_CIT0034","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1002\/sim.2929","article-title":"Evaluating the added predictive ability of a new marker: From area under the ROC curve to reclassification and beyond","volume":"27","author":"Pencina","year":"2008","journal-title":"Stat Med."},{"issue":"6","key":"2022092808430659500_CIT0035","doi-asserted-by":"crossref","first-page":"796","DOI":"10.1016\/j.eururo.2018.08.038","article-title":"Reporting and interpreting decision curve analysis: a guide for investigators","volume":"74","author":"Van Calster","year":"2018","journal-title":"Eur Urol."},{"issue":"3","key":"2022092808430659500_CIT0036","doi-asserted-by":"crossref","first-page":"1345","DOI":"10.1093\/jme\/tjaa282","article-title":"Validating species distribution models with standardized surveys for Ixodid ticks in mainland Florida","volume":"58","author":"Glass","year":"2021","journal-title":"J Med Entomol."},{"issue":"11","key":"2022092808430659500_CIT0037","doi-asserted-by":"crossref","first-page":"1","DOI":"10.18637\/jss.v036.i11","article-title":"Feature selection with the Boruta package","volume":"36","author":"Kursa","year":"2010","journal-title":"J Stat Softw."},{"key":"2022092808430659500_CIT0038","doi-asserted-by":"crossref","DOI":"10.1145\/3314074.3314076","article-title":"Performance of statistical models to predict vitamin D levels","author":"Bechrouri","year":"2019"},{"key":"2022092808430659500_CIT0039","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1016\/j.jsbmb.2018.12.012","article-title":"Impact of high latitude, urban living and ethnicity on 25-hydroxyvitamin D status: a need for multidisciplinary action?","volume":"188","author":"Mendes","year":"2019","journal-title":"J Steroid Biochem Mol Biol."},{"issue":"5","key":"2022092808430659500_CIT0040","doi-asserted-by":"crossref","first-page":"644","DOI":"10.1111\/j.1651-2227.2006.00178.x","article-title":"Understanding diagnostic tests 3: receiver operating characteristic curves","volume":"96","author":"Akobeng","year":"2007","journal-title":"Acta Paediatr."},{"issue":"1","key":"2022092808430659500_CIT0041","first-page":"22","article-title":"Cohort Profile: The PREDICT cardiovascular disease cohort in New Zealand primary care (PREDICT-CVD 19)","volume":"46","author":"Wells","year":"2017","journal-title":"Int J Epidemiol."},{"issue":"3","key":"2022092808430659500_CIT0042","doi-asserted-by":"crossref","first-page":"e12340","DOI":"10.1111\/mcn.12340","article-title":"Predictors of vitamin D status in New Zealand preschool children","volume":"13","author":"Cairncross","year":"2017","journal-title":"Matern Child Nutr."}],"container-title":["The Journal of Clinical Endocrinology &amp; Metabolism"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jcem\/advance-article-pdf\/doi\/10.1210\/clinem\/dgac432\/45294839\/dgac432.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcem\/article-pdf\/107\/10\/2737\/46112900\/dgac432.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jcem\/article-pdf\/107\/10\/2737\/46112900\/dgac432.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,24]],"date-time":"2023-11-24T18:06:33Z","timestamp":1700849193000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jcem\/article\/107\/10\/2737\/6649573"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,7,25]]},"references-count":42,"journal-issue":{"issue":"10","published-online":{"date-parts":[[2022,7,25]]},"published-print":{"date-parts":[[2022,9,28]]}},"URL":"https:\/\/doi.org\/10.1210\/clinem\/dgac432","relation":{},"ISSN":["0021-972X","1945-7197"],"issn-type":[{"value":"0021-972X","type":"print"},{"value":"1945-7197","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2022,10,1]]},"published":{"date-parts":[[2022,7,25]]}}}